Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, idempotentHint, and destructiveHint. The description reinforces these with 'Every call is read-only and idempotent' and adds extra behavioral context: the tool never raises a protocol error on bad input but returns an error object. This gives the agent a clear expectation of the tool's failure mode, which is beyond what annotations alone offer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured: a single-sentence purpose statement, a concise example, usage guidelines, error behavior, and a concluding note on idempotency. Every sentence adds useful information; there is no filler. The most critical information (purpose and when to use) appears first, fitting the front-loading principle.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (statistical test with four integer parameters), the description is complete. It covers what the tool does, when to use it (and when not), error handling, and a sample output that illustrates the return fields (rate_pct, p_value, verdict, etc.). The presence of an output schema (per context signals) further reduces risk, but the description alone already paints a clear picture.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage, so each parameter is already documented. The description adds value by providing a typical input example (e.g., '{

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool 'Run a two-proportion A/B significance test with a plain-language verdict.' This is a specific verb (Run) and resource (A/B significance test), with an explicit output characteristic (plain-language verdict). The example input/output further clarifies the goal, and the tool is distinct from sibling tools like cohort_retention or correlation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use: 'Use when exactly two variants each have a trial count and a conversion count.' It also gives exclusion criteria: 'Not for continuous outcomes such as revenue per user, and not for three or more variants.' Additionally, it explains error-handling behavior ('returns {

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.